Chart: Cleveland Dot Plot

Overview

Cleveland dot plots are a convenient alternative to bar plots, particularly for datasets with large numbers of categories.

With ggplot2, it’s helpful to create a dot plot theme, which can be reused:

## Cleveland Dot Plot theme
library(tidyverse)

## ── Attaching packages ───────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 2.2.1.9000     ✔ purrr   0.2.5     
## ✔ tibble  1.4.2          ✔ dplyr   0.7.6     
## ✔ tidyr   0.8.1          ✔ stringr 1.3.1     
## ✔ readr   1.1.1          ✔ forcats 0.3.0

## Warning: package 'dplyr' was built under R version 3.5.1

## ── Conflicts ──────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

theme_dotplot <- theme_bw(18) +
    theme(axis.text.y = element_text(size = rel(.75)),
          axis.ticks.y = element_blank(),
          axis.title.x = element_text(size = rel(.75)),
          panel.grid.major.x = element_blank(),
          panel.grid.major.y = element_line(size = 0.5),
          panel.grid.minor.x = element_blank())

Cleveland dot plot

world <-  read_csv("https://raw.githubusercontent.com/jtr13/codehelp/master/data/countries2012.csv")

## Parsed with column specification:
## cols(
##   COUNTRY = col_character(),
##   CONTINENT = col_character(),
##   GDP = col_double(),
##   TFR = col_double(),
##   LIFEEXP = col_double(),
##   CHMORT = col_double()
## )

africa <- world %>% filter(CONTINENT == "Africa")

ggplot(africa, aes(x = GDP, y = fct_reorder(COUNTRY, GDP))) +
    geom_point(color = "blue") + ylab("") +
    theme_dotplot + ggtitle("Africa: GDP per capita, 2012")

Multiple dots

library(AER)
data("USSeatBelts")
belts <- USSeatBelts %>% 
    filter(year %in% c(1983, 1997)) %>% 
    select(state, year, fatalities) 
 
ggplot(belts, aes(x = fatalities, 
                  y = fct_reorder2(state, year, -fatalities), 
                  color = year)) + 
    geom_point() + ylab("") + theme_dotplot + 
    ggtitle("Number of fatalities per million traffic miles")

Large number of categories

Scroll

In chunk options: {r fig.height = 20}

g <- ggplot(world, aes(x = GDP, y = fct_reorder(COUNTRY, GDP))) +
    geom_point(color = "blue") + ylab("") +
    theme_dotplot
g

Interactive Cleveland dot plot

library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

ggplotly(g)

library(ggplot2)
# create dot plot theme
theme_dotplot <- theme_bw(18) +
    theme(axis.text.y = element_text(size = rel(.8)),
          axis.ticks.y = element_blank(),
          axis.title.x = element_text(),
          axis.text = element_text(face = "bold"),
          plot.background = element_rect(fill = "lightcyan2"),
          panel.background = element_rect(fill = "moccasin"),
          panel.grid.major.x = 
              element_line(size = 0.5),
          panel.grid.major.y = 
              element_line(size = 0.5, color = "lightblue"),
          panel.grid.minor.x = element_blank(),
          strip.text = element_text(size = rel(.7)),
          legend.position = "top")

# data source:
# NYT, How Much People in the Trump Administration Are Worth
# https://www.nytimes.com/interactive/2017/04/01/us/politics/how-much-people-in-the-trump-administration-are-worth-financial-disclosure.html
df <-  read_csv("https://raw.githubusercontent.com/jtr13/codehelp/master/data/Assets.csv")

## Parsed with column specification:
## cols(
##   Name = col_character(),
##   Assets = col_integer()
## )

# change units to millions
df$Assets <- df$Assets / 1000000

# sort names by assets
df$Name <- reorder(df$Name, df$Assets)

# Cleveland Dot Plot

ggplot(df, aes(x = Assets, y = Name)) +
    geom_point() + 
    ggtitle("How Much People in the Trump\nAdministration Are Worth") +
    ylab("") + xlab("Assets in Millions $") +
    theme_dotplot

# Cleveland Dot Plot with Four Panels

# create Panel column
df$Panel <- rep(1:4, each = 9)
df$Panel <- factor(df$Panel, levels = 1:4, 
                   labels = c("$18 Million+",
                                        "$4 - 12 Million",
                                        "$1 - 3.5 Million",
                                        "$66k - $604k"))
                                        
ggplot(df, aes(x = Assets, y = Name)) +
    geom_point() + facet_wrap(~Panel, scales = "free", 
                              ncol = 1) +
    ggtitle("How Much People in the Trump\nAdministration Are Worth") +
    ylab("") + xlab("Assets in Millions $") +
    theme_dotplot